Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    common word pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jackets
    0.46
    вли
    0.45
    était
    0.45
     возгла
    0.44
    ក្ល
    0.44
    茵
    0.44
    łu
    0.43
     היה
    0.43
    τε
    0.43
    szyst
    0.42
    POSITIVE LOGITS
     occasional
    0.48
     ตาม
    0.42
     Examples
    0.41
     ويمكن
    0.41
     نو
    0.40
     学習
    0.39
     gerne
    0.39
     interleaved
    0.39
     according
    0.39
     อาจ
    0.39
    Act Density 0.006%

    No Known Activations